Co-Advisor

Gao Huang

Gao Huang is an Associate Professor at Tsinghua University, specializing in deep learning, neural networks, and reinforcement learning. His notable work includes DenseNet, which won the CVPR Best Paper Award in 2017. He is also known for his contributions to efficient deep learning and dynamic neural networks.

Dynamic neural networksEfficient deep learning

Yizeng Han

Yizeng Han is a co-advised PhD student, starting his research in September 2018. His research interests include dynamic neural networks and efficient deep learning.

Dynamic neural networksEfficient deep learning

Shenzhi Wang

Shenzhi Wang is a co-advised PhD student, beginning his research in September 2021. His research focuses on reinforcement learning, robotics, and anomaly detection in computer vision. He has a strong interest in applying these techniques to real-world problems.

Reinforcement LearningRoboticsAnomaly Detection in Computer Vision

Andrew Zhao

Andrew Zhao is a PhD student at Tsinghua University, starting his research in 2021. His research interests lie in reinforcement learning, with a particular focus on generalization and multitask learning.

Reinforcement Learninggeneralizationmultitask learning

Matthieu Lin

Matthieu Lin is a co-advised PhD student at Tsinghua University, beginning his research in September 2021. His research interests are in large language models (LLMs) and reinforcement learning. He is exploring the intersection of these two fields to develop more advanced AI systems.

LLMReinforcement Learning

Rui Huang

Rui Huang is a co-advised PhD student at Tsinghua University, beginning his research in September 2020. His research focuses on dynamic neural networks and efficient neural networks. He is interested in developing novel architectures and techniques to improve the performance and efficiency of deep learning models.

Dynamic neural networksEfficient neural networks

Zhuofan Xia

Zhuofan Xia is a co-advised Master's student at Tsinghua University. He graduated with a Bachelor of Engineering degree from Tsinghua University in 2020. His research interests are in 3D Vision and fundamental vision, focusing on developing algorithms and techniques for understanding and analyzing 3D data.

3D Visionfundamental vision

Xuran Pan

Xuran Pan is a co-advised PhD student at Tsinghua University, beginning his research in September 2018. His research interests include network architecture design and 3D vision. He is passionate about developing efficient and effective deep learning models for tasks involving 3D data.

Network architecture design3D vision

Jiayi Guo

Jiayi Guo is a co-advised PhD student at Tsinghua University, beginning his research in September 2020. He received his Bachelor of Engineering degree from Tsinghua University in 2020. His research interests lie in generative models and efficient neural networks, focusing on developing new techniques for generating realistic data and improving the efficiency of deep learning models.

Generative modelsefficient neural networks

Yang Yue

Yang Yue is a co-advised PhD student at Tsinghua University. His research interests are in deep reinforcement learning, particularly in the areas of world models and embodied AI. He is focused on developing intelligent agents that can learn and adapt to complex environments.

deep reinforcement learningworld modelembodied ai

Qisen Yang

Qisen Yang is a co-advised student at Tsinghua University. His research interests are in deep reinforcement learning and efficient deep learning. He is focused on developing algorithms that can learn complex behaviors efficiently and effectively.

Deep reinforcement learningefficient deep learning

Honghui Wang

Honghui Wang is a co-advised student at Tsinghua University. He received his Bachelor of Engineering degree from Tsinghua University in 2020. His research interests are in dynamic neural networks and self-supervised learning. He is focused on developing models that can learn effectively from unlabeled data and adapt to changing environments.

Dynamic neural networksself-supervised learning

Chenxin Tao

Chenxin Tao is a co-advised student at Tsinghua University. His research interests are in AutoML and self-supervised learning. He is focused on developing techniques that can automate the process of designing and training deep learning models and improve their performance through self-learning.

automlself - supervised learning

Chaofei Wang

Chaofei Wang is a co-advised PhD student at Tsinghua University, beginning his research in September 2018. His research interests are in few-shot learning and efficient deep learning. He is focused on developing models that can learn effectively from limited data and perform well in resource-constrained environments.

Few shot learningefficient deep learning

Yulin Wang

Yulin Wang is a PhD Student at Tsinghua University, beginning his research in September 2019. He received his Bachelor of Engineering degree from Beihang University in 2019. His research interests are in dynamic neural networks and efficient deep learning. He is focused on developing models that can adapt to changing environments and perform well with limited computational resources.

Dynamic neural networksefficient deep learning

Chunjiang Ge

Chunjiang Ge is a co-advised student at Tsinghua University. He is currently pursuing his PhD, beginning in 2020, and previously earned his Bachelor of Science degree from Tsinghua University in 2020. His research interests are in causal inference, computer vision, and machine learning. He is focused on developing methods to understand and analyze the causal relationships between different factors in complex systems, particularly in the context of computer vision.

Causal InferenceComputer VisionMachine Learning

Wanlu Yang

Wanlu Yang is a co-advised student at Tsinghua University. His research interests are in reinforcement learning and operation research. He is focused on developing algorithms that can effectively solve optimization problems in complex dynamic environments.

Reinforcement LearningOperation Research

Peng Jiang

Peng Jiang is a co-advised student at Tsinghua University. He earned his Bachelor's degree from Beijing Jiaotong University in 2017 and began his PhD program at Tsinghua University in the same year. His research interests are in reinforcement learning, operation research, and autonomous underwater vehicle control. He is focused on developing intelligent control systems for underwater vehicles.

Reinforcement learningoperation researchautonomous underwater vehicle control

Wenjie Shi

Wenjie Shi is a co-advised student at Tsinghua University. His research interests are in deep reinforcement learning and interpretability. He is focused on developing algorithms that can not only learn effective behaviors but also provide insights into their decision-making processes.

Deep Reinforcement LearningInterpretability

Hangkai Hu

Hangkai Hu is a co-advised student at Tsinghua University. His research interests are in meta-reinforcement learning and multi-agent reinforcement learning. He is focused on developing algorithms that can learn from past experiences to adapt quickly to new tasks or environments and enable multiple agents to collaborate effectively to achieve shared goals.

Meta Reinforcement LearningMulti-Agent Reinforcement Learning

Student

Yukang Yang

Yukang Yang is a Master's student at Tsinghua University, beginning his studies in September 2019. His research interests are in machine learning-based medical image analysis and efficient deep learning. He is focused on developing algorithms that can effectively analyze medical images to improve diagnosis and treatment outcomes.

Machine learning-based medical image analysisEfficient deep learning

Chaoqun Du

Chaoqun Du is a PhD student at Tsinghua University, beginning his research in September 2020. His research interests are in long-tailed learning, semi-supervised learning, and machine learning. He is focused on developing algorithms that can effectively learn from imbalanced datasets and generalize well to unseen data.

Long-tailed learningSemi-supervised learningMachine learning

Haojun Jiang

Haojun Jiang is a PhD student at Tsinghua University, beginning his research in September 2020. His research interests are in efficient neural networks, dynamic neural networks, and multi-modality learning. He is focused on developing models that can learn effectively from multiple sources of data and perform well with limited computational resources.

Efficient neural networksDynamic neural networksMulti-modality learning

Yifan Pu

Yifan Pu is a student at Tsinghua University. His research interests are in efficient neural networks. He is focused on developing algorithms that can improve the performance and efficiency of deep learning models, particularly in resource-constrained environments.

Efficient Neural Networks

Yong Xien Chng

Yong Xien Chng is a PhD student at Tsinghua University, beginning his research in September 2020. His research interests are in efficient deep learning. He is focused on developing techniques that can improve the performance and efficiency of deep learning models, particularly in resource-constrained environments.

Efficient deep learning

Rui Lu

Rui Lu is a PhD student at Tsinghua University, beginning his research in September 2021. His research interests are in deep learning-based computer vision, reinforcement learning, efficient deep learning algorithm design, and theoretical understanding. He is focused on developing algorithms that can effectively solve real-world problems by combining theoretical rigor with practical applications.

Deep Learning Based Computer VisionReinforcement LearningEfficient Deep Learning Algorithm DesignTheoretical Understanding

Yang Yue

Yang Yue is a PhD student at Tsinghua University, beginning his research in September 2022.

Zanlin Ni

Zanlin Ni is a PhD student at Tsinghua University, beginning his research in September 2022. His research interests are in deep learning and computer vision. He is focused on developing algorithms that can effectively analyze and understand visual information.

Deep LearningComputer Vision